Hedwig : A named entity linker
(2020) 12th International Conference on Language Resources and Evaluation, LREC 2020 In LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings p.4501-4508- Abstract
Named entity linking is the task of identifying mentions of named things in text, such as “Barack Obama” or “New York”, and linking these mentions to unique identifiers. In this paper, we describe Hedwig, an end-to-end named entity linker, which uses a combination of word and character BILSTM models for mention detection, a Wikidata and Wikipedia-derived knowledge base with global information aggregated over nine language editions, and a PageRank algorithm for entity linking. We evaluated Hedwig on the TAC2017 dataset, consisting of news texts and discussion forums, and we obtained a final score of 59.9% on CEAFmC+, an improvement over our previous generation linker Ugglan, and a trilingual entity link score of 71.9%.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1bd6c347-8ed2-4c32-923f-a352af1bff6a
- author
- Klang, Marcus LU and Nugues, Pierre LU
- organization
- publishing date
- 2020
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Named entity annotation, Named entity linking, Named entity recognition
- host publication
- LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
- series title
- LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
- editor
- Calzolari, Nicoletta ; Bechet, Frederic ; Blache, Philippe ; Choukri, Khalid ; Cieri, Christopher ; Declerck, Thierry ; Goggi, Sara ; Isahara, Hitoshi ; Maegaard, Bente ; Mariani, Joseph ; Mazo, Helene ; Moreno, Asuncion ; Odijk, Jan and Piperidis, Stelios
- pages
- 8 pages
- publisher
- European Language Resources Association
- conference name
- 12th International Conference on Language Resources and Evaluation, LREC 2020
- conference location
- Marseille, France
- conference dates
- 2020-05-11 - 2020-05-16
- external identifiers
-
- scopus:85096580434
- ISBN
- 9791095546344
- language
- English
- LU publication?
- yes
- id
- 1bd6c347-8ed2-4c32-923f-a352af1bff6a
- alternative location
- https://www.aclweb.org/anthology/2020.lrec-1.554.pdf
- date added to LUP
- 2020-12-08 11:29:34
- date last changed
- 2022-04-19 02:35:13
@inproceedings{1bd6c347-8ed2-4c32-923f-a352af1bff6a, abstract = {{<p>Named entity linking is the task of identifying mentions of named things in text, such as “Barack Obama” or “New York”, and linking these mentions to unique identifiers. In this paper, we describe Hedwig, an end-to-end named entity linker, which uses a combination of word and character BILSTM models for mention detection, a Wikidata and Wikipedia-derived knowledge base with global information aggregated over nine language editions, and a PageRank algorithm for entity linking. We evaluated Hedwig on the TAC2017 dataset, consisting of news texts and discussion forums, and we obtained a final score of 59.9% on CEAFmC+, an improvement over our previous generation linker Ugglan, and a trilingual entity link score of 71.9%.</p>}}, author = {{Klang, Marcus and Nugues, Pierre}}, booktitle = {{LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings}}, editor = {{Calzolari, Nicoletta and Bechet, Frederic and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, Helene and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}}, isbn = {{9791095546344}}, keywords = {{Named entity annotation; Named entity linking; Named entity recognition}}, language = {{eng}}, pages = {{4501--4508}}, publisher = {{European Language Resources Association}}, series = {{LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings}}, title = {{Hedwig : A named entity linker}}, url = {{https://www.aclweb.org/anthology/2020.lrec-1.554.pdf}}, year = {{2020}}, }